Disentangling Visual Embeddings with Minimal Distributional Assumptions. (arXiv:2206.13872v2 [stat.ML] UPDATED)

Interest in understanding and factorizing embedding spaces learned by deep
encoders is growing. Concept discovery methods search the embedding spaces for
interpretable latent components like object shape or color and disentangle them
into individual axes in the embedding space. Yet, the applicability of modern
disentanglement learning techniques or independent component analysis (ICA) is
limited when it comes to vision tasks: They either require training a model of
the complex image-generating process or their rigid stochastic independence
assumptions on the component …

arxiv assumptions